Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Premise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ֹ
    0.46
     cuya
    0.45
    ამდე
    0.43
     portanto
    0.42
    hetically
    0.42
    ؟؟
    0.42
    usten
    0.42
     dictionary
    0.41
    ણ
    0.41
    писа
    0.41
    POSITIVE LOGITS
     Parks
    0.52
     Hegel
    0.50
     Rol
    0.49
     Elephant
    0.49
     Truck
    0.49
     Augustus
    0.49
     Aiden
    0.49
     Pixar
    0.48
     Braun
    0.47
     Pork
    0.47
    Act Density 0.003%

    No Known Activations